阅读说明：本技术 一种基于声音识别生理现象的装置 (Device based on sound identification physiology phenomenon ) 是由 赵隆超 孙彩昕 罗竟成 董辉 于 2021-10-15 设计创作，主要内容包括：本发明提供了一种基于声音识别生理现象的装置。包括：导管,与患者呼吸导管连接,呼吸气体流经导管；拾音器,用于实时采集接收导管所传送的声音,对所述声音进行放大处理,生成处理音频；声音传感器,用于接收所述处理音频,并转换为电信号；导线,用于连接音频处理装置和声音传感器；音频处理装置,用于对所述电信号进行声音特征分离,确定非语言声音特征,对所述非语音声音特征进行处理,并匹配不同的处理设备。(The invention provides a device for recognizing physiological phenomena based on voice. The method comprises the following steps: a conduit connected to a patient breathing conduit through which breathing gas flows; the sound pickup is used for collecting and receiving the sound transmitted by the catheter in real time, amplifying the sound and generating a processed audio frequency; the sound sensor is used for receiving the processed audio and converting the processed audio into an electric signal; a wire for connecting the audio processing device and the sound sensor; and the audio processing device is used for carrying out sound characteristic separation on the electric signal, determining non-language sound characteristics, processing the non-voice sound characteristics and matching different processing equipment.)

1. An apparatus for recognizing a physiological phenomenon based on a voice, comprising:

duct (1): connected to a patient breathing conduit through which breathing gas flows (1);

microphone (2): the system is used for collecting and receiving the sound transmitted by the catheter (1) in real time, amplifying the sound and generating a processed audio;

acoustic sensor (3): the audio processing device is used for receiving the processed audio and converting the processed audio into an electric signal;

wire (4): the voice processing device is used for connecting the voice processing device with the voice sensor;

audio processing apparatus (5): the voice recognition device is used for carrying out voice feature separation on the electric signals, determining non-language voice features, processing the non-voice features and matching different processing devices.

2. The apparatus for recognizing a physiological phenomenon based on a voice as set forth in claim 1, wherein the sound pickup comprises:

the sound collector comprises: the system is used for acquiring and receiving scene sound in real time within a target detection range;

the audio frequency restorer: and the system is used for restoring the frequency and the amplitude of the sound of the scene sound through a frequency selection network.

3. The device of claim 1, wherein the acoustic sensor comprises:

an amplitude tester: the device comprises a detection module, a comparison module and a comparison module, wherein the detection module is used for carrying out amplitude detection on the audio frequency of the collected sound, comparing the amplitude with the amplitude of the physiological phenomenon sample audio frequency, carrying out first pre-classification on the audio frequency, and determining the physiological phenomenon audio frequency and the common audio frequency;

frequency sweep signal appearance: the audio frequency is subjected to frequency detection, and the sound is subjected to second pre-classification by comparing with the frequency of the physiological phenomenon sample audio frequency to determine the physiological phenomenon audio frequency and the common audio frequency;

a signal processor: and the device is used for converting the physiological phenomenon audio and the common audio determined by the first pre-classification and the second pre-classification into physiological phenomenon electric signals and transmitting the physiological phenomenon electric signals to an audio processing device.

4. The device for recognizing a physiological phenomenon based on a voice as claimed in claim 1, wherein the audio processing device comprises:

a noise remover: the physiological phenomenon electric signal is used for purifying the physiological phenomenon electric signal through a self-adaptive filter to obtain a pure physiological phenomenon electric signal;

an end point tester: the physiological phenomenon electric signal testing device is used for carrying out signal end point testing on the physiological phenomenon electric signal and determining the initial position of the physiological phenomenon electric signal;

a frame separator: and the device is used for framing the electric signal from the initial position of the physiological phenomenon electric signal, averagely dividing the electric signal into short-time stationary signals of small sections, and performing subsection analysis on the short-time stationary signals to obtain characteristic parameters.

5. The device for recognizing a physiological phenomenon based on a voice as claimed in claim 4, wherein the audio processing device further comprises:

characteristic parameter extraction instrument: the method comprises the steps of extracting key characteristic parameters of short-time stationary signals of physiological phenomena by sensing linear prediction coefficients;

physiological phenomenon audio memory: the physiological phenomenon electric signal sampling device is used for storing a physiological phenomenon electric signal sample acquired in reality and key characteristic parameters of the sample, and storing a threshold value set by the key characteristic parameters;

physiological sound signal classification device: the short-time stationary signal classification method is used for sampling key characteristic parameters of the short-time stationary signal and classifying the short-time stationary signal according to the comparison between the sampling and the threshold value.

6. The apparatus for recognizing a physiological phenomenon based on a voice as set forth in claim 1, wherein the physiological sound signal classification device comprises:

characteristic parameter analysis equipment: classifying the short-time stationary signals into cough short-time stationary signals, sigh short-time stationary signals and unvoiced sound short-time stationary signals according to the comparison result, and matching different processing modes according to the classification;

matching equipment: and the signal processing mode is used for receiving and matching the classified signals.

7. The apparatus for recognizing a physiological phenomenon based on a voice as set forth in claim 1, wherein the matching device comprises:

cough electrical signal processor: the device is used for sending out a delay operation initial command to the detected cough electric signal, and different operation commands can be set according to different devices;

sigh electrical signal processor: the system is used for sending a slowing operation initial command to the detected sigh electric signal, and different operation commands can be set according to different equipment;

the throat-clearing sound electric signal processor: the voice detector is used for sending a pause operation initial command to the detected unvoiced sound electric signal, and different operation commands can be set according to different devices.

8. The device for recognizing a physiological phenomenon based on voice as claimed in claim 1, wherein the endpoint tester comprises the steps of:

s1: determining the condition of a starting point in the detection process, and discharging a blank voice section according to the mean value of the spectral entropy;

s2: after a physiological phenomenon sound endpoint is detected, a back-end self-adaptive threshold is adopted, and a threshold value is adjusted to a proper value;

s3: determining the short-time energy and average zero-crossing rate threshold of each frame according to the characteristics of the physiological phenomenon sound, and determining a physiological phenomenon sound endpoint;

s4, calculating the number of the zero crossing rate of the first 20 frames lower than the threshold value of the zero crossing rate, and calculating the average spectral entropy of the first 20 frames;

s5: and (4) judging whether the zero-crossing rate number and the average spectral entropy of the first 20 frames reach the standard, if so, finishing the end point detection, otherwise, continuing the next end point detection, and turning to the step S1.

9. The device for recognizing a physiological phenomenon based on a voice as claimed in claim 1, wherein the audio processing device further comprises:

the non-voice sound signal detector comprises: the method is used for analyzing the sound signals emitted by the organs or joints of the human body, determining the distribution of the physiological sound signals in the frequency domain, and performing frequency spectrum analysis on the organs or joints according to the frequency domain information to determine the illness state of the patient.

10. The device for recognizing a physiological phenomenon based on a voice as claimed in claim 4, wherein the audio processing device further comprises:

a signal doubler: after the noise eliminator, the high-frequency part of the pure electric signal is pre-emphasized through A/D conversion, and the dynamic range of the physiological phenomenon sound signal is compressed to obtain a high signal-to-noise ratio which is used for enhancing the physiological phenomenon sound signal.

Technical Field

The invention relates to the technical field of voice recognition, in particular to a device for recognizing physiological phenomena based on voice.

Background

At present, cough is the main symptom of respiratory diseases, and many diseases have cough symptoms, when the patients are possibly treated by a respirator, sudden physiological phenomena such as sigh and cough occur occasionally in the patients breathing by the respirator. In some breathing modes (forced breathing and the like), when a patient breathes due to the above physiological phenomenon, the gas sent to the patient by the breathing machine collides with the patient, so that the patient cannot fully exhale or hold breath, and severe cough or oxygen deficiency of the patient can be caused, thereby endangering the life safety of the patient. Therefore, the ventilator needs to predict the physiological phenomenon of the patient and perform operations such as delayed ventilation.

At present, when a physiological phenomenon is identified by voice, the identification of the physiological phenomenon according to process quantity parameters such as respiratory flow, pressure and the like needs to be based on big data analysis, but the judgment is not accurate and the misjudgment rate is high.

Disclosure of Invention

The invention provides a device for recognizing physiological phenomena based on voice, which is used for recognizing the physiological phenomena by using voice and processing emergencies.

An apparatus for recognizing a physiological phenomenon based on a voice, comprising:

duct (1): connected to a patient breathing conduit through which breathing gas flows (1);

microphone (2): the system is used for collecting and receiving the sound transmitted by the catheter (1) in real time, amplifying the sound and generating a processed audio;

acoustic sensor (3): the audio processing device is used for receiving the processed audio and converting the processed audio into an electric signal; wire (4): the voice processing device is used for connecting the voice processing device with the voice sensor;

audio processing apparatus (5): the voice recognition device is used for carrying out voice feature separation on the electric signals, determining non-language voice features, processing the non-voice features and matching different processing devices.

Further, the sound pickup includes:

the sound collector comprises: the system is used for acquiring and receiving scene sound in real time within a target detection range;

the audio frequency restorer: and the system is used for restoring the frequency and the amplitude of the sound of the scene sound through a frequency selection network.

Further, the sound sensor includes:

an amplitude tester: the device comprises a detection module, a comparison module and a comparison module, wherein the detection module is used for carrying out amplitude detection on the audio frequency of the collected sound, comparing the amplitude with the amplitude of the physiological phenomenon sample audio frequency, carrying out first pre-classification on the audio frequency, and determining the physiological phenomenon audio frequency and the common audio frequency;

frequency sweep signal appearance: the audio frequency is subjected to frequency detection, and the sound is subjected to second pre-classification by comparing with the frequency of the physiological phenomenon sample audio frequency to determine the physiological phenomenon audio frequency and the common audio frequency;

a signal processor: and the device is used for converting the physiological phenomenon audio and the common audio determined by the first pre-classification and the second pre-classification into physiological phenomenon electric signals and transmitting the physiological phenomenon electric signals to an audio processing device.

Further, the audio processing apparatus includes:

a noise remover: the physiological phenomenon electric signal is used for purifying the physiological phenomenon electric signal through a self-adaptive filter to obtain a pure physiological phenomenon electric signal;

an end point tester: the physiological phenomenon electric signal testing device is used for carrying out signal end point testing on the physiological phenomenon electric signal and determining the initial position of the physiological phenomenon electric signal;

a frame separator: and the device is used for framing the electric signal from the initial position of the physiological phenomenon electric signal, averagely dividing the electric signal into short-time stationary signals of small sections, and performing subsection analysis on the short-time stationary signals to obtain characteristic parameters.

Further, the audio processing apparatus further includes:

characteristic parameter extraction instrument: the method comprises the steps of extracting key characteristic parameters of short-time stationary signals of physiological phenomena by sensing linear prediction coefficients;

physiological phenomenon audio memory: the physiological phenomenon electric signal sampling device is used for storing a physiological phenomenon electric signal sample acquired in reality and key characteristic parameters of the sample, and storing a threshold value set by the key characteristic parameters;

physiological sound signal classification device: the short-time stationary signal classification method is used for sampling key characteristic parameters of the short-time stationary signal and classifying the short-time stationary signal according to the comparison between the sampling and the threshold value.

Further, the physiological sound signal classification device includes:

characteristic parameter analysis equipment: classifying the short-time stationary signals into cough short-time stationary signals, sigh short-time stationary signals and unvoiced sound short-time stationary signals according to the comparison result, and matching different processing modes according to the classification;

matching equipment: and the signal processing mode is used for receiving and matching the classified signals.

Further, the matching apparatus includes:

cough electrical signal processor: the device is used for sending out a delay operation initial command to the detected cough electric signal, and different operation commands can be set according to different devices;

sigh electrical signal processor: the system is used for sending a slowing operation initial command to the detected sigh electric signal, and different operation commands can be set according to different equipment;

the throat-clearing sound electric signal processor: the voice detector is used for sending a pause operation initial command to the detected unvoiced sound electric signal, and different operation commands can be set according to different devices.

Further, the end point tester comprises the following steps:

s1: determining the condition of a starting point in the detection process, and discharging a blank voice section according to the mean value of the spectral entropy;

s2: after a physiological phenomenon sound endpoint is detected, a back-end self-adaptive threshold is adopted, and a threshold value is adjusted to a proper value;

s3: determining the short-time energy and average zero-crossing rate threshold of each frame according to the characteristics of the physiological phenomenon sound, and determining a physiological phenomenon sound endpoint;

s4, calculating the number of the zero crossing rate of the first 20 frames lower than the threshold value of the zero crossing rate, and calculating the average spectral entropy of the first 20 frames;

s5: and (4) judging whether the zero-crossing rate number and the average spectral entropy of the first 20 frames reach the standard, if so, finishing the end point detection, otherwise, continuing the next end point detection, and turning to the step S1.

Further, the audio processing apparatus further includes:

the non-voice sound signal detector comprises: the method is used for analyzing the sound signals emitted by the organs or joints of the human body, determining the distribution of the physiological sound signals in the frequency domain, and performing frequency spectrum analysis on the organs or joints according to the frequency domain information to determine the illness state of the patient.

Further, the audio processing apparatus further includes:

a signal doubler: after the noise eliminator, the high-frequency part of the pure electric signal is pre-emphasized through A/D conversion, and the dynamic range of the physiological phenomenon sound signal is compressed to obtain a high signal-to-noise ratio which is used for enhancing the physiological phenomenon sound signal.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.

The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:

FIG. 1 is a schematic diagram of a device for recognizing physiological phenomena based on voice according to an embodiment of the present invention;

FIG. 2 is a graph illustrating an amplitude variation of a physiological phenomenon sound signal based on sound recognition of a physiological phenomenon according to an embodiment of the present invention;

FIG. 3 is a flowchart of an endpoint tester for recognizing physiological phenomena based on voice in accordance with an embodiment of the present invention. (ii) a

Detailed Description

The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.

Example 1:

an embodiment of the present invention provides a device for recognizing a physiological phenomenon based on a voice, as shown in fig. 1, including:

duct (1): connected to a patient breathing conduit through which breathing gas flows (1);

microphone (2): the system is used for collecting and receiving the sound transmitted by the catheter (1) in real time, amplifying the sound and generating a processed audio;

acoustic sensor (3): the audio processing device is used for receiving the processed audio and converting the processed audio into an electric signal;

wire (4): the voice processing device is used for connecting the voice processing device with the voice sensor;

audio processing apparatus (5): the voice recognition device is used for carrying out voice feature separation on the electric signals, determining non-language voice features, processing the non-voice features and matching different processing devices.

The working principle of the technical scheme is as follows:

the device comprises a sound pickup, an audio processing device, a physiological phenomenon sound processing device and a physiological phenomenon sound processing device, wherein the sound pickup collects and transmits field sound to the sound pickup through a conduit, the sound pickup amplifies the amplitude and frequency of the field sound and transmits processed audio to a sound sensor to convert an electric signal, the audio processing device receives the electric signal, extracts characteristic parameters of the audio electric signal and detects end points, and the physiological phenomenon sound is classified and matched with different processing modes.

The beneficial effects of the above technical scheme are: the invention discloses an automatic device for non-fixed individuals aiming at physiological phenomenon sound, which detects and separates the physiological phenomenon sound from audio frequency containing a large amount of speaking voice and sound with similar characteristics, classifies the physiological phenomenon sound according to the frequency, amplitude and characteristics of the physiological phenomenon voice, and processes the physiological phenomenon sound according to classification matching corresponding processing equipment.

Example 2:

in one embodiment, the sound pickup includes:

the sound collector comprises: the system is used for acquiring and receiving scene sound in real time within a target detection range;

the audio frequency restorer: and the system is used for restoring the frequency and the amplitude of the sound of the scene sound through a frequency selection network.

The working principle of the technical scheme is as follows:

the sound receiver transmits the sound to the gathering together through the sound collecting element, the audio amplifier mainly plays a role in restoring the audio amplification of the sound to the original sound or a state close to the original sound, can collect and amplify the sound and can play a certain role in eliminating noise, the sound pick-up can work because on a simple and efficient frequency selection network arranged in the sound pick-up, the frequency network can selectively filter the sound with different frequencies, pick out and retain the sound needed to be collected by people, the frequencies needed to be collected are preserved, the frequencies of other sounds are different from the frequencies needed to be retained, therefore, other noise enters the microphone and is filtered after passing through the frequency selection network, and the sound needed to be collected by people is retained through the frequency selection network and is restored through the audio amplifying device, the original sound is maintained.

The beneficial effects of the above technical scheme are: the sound collecting device adopts the sound pick-up as the sound collecting equipment of the device, the sound pick-up has high sensitivity and can collect fine sound on site, and meanwhile, the sound pick-up is omnidirectional and can collect the sound in the whole monitoring space, thereby ensuring the comprehensive and clear collected sound on site.

Example 3:

in one embodiment, shown in fig. 2, the sound sensor is a graph of amplitude variation of a physiological phenomenon sound signal, and comprises:

an amplitude tester: the device comprises a detection module, a comparison module and a comparison module, wherein the detection module is used for carrying out amplitude detection on the audio frequency of the collected sound, comparing the amplitude with the amplitude of the physiological phenomenon sample audio frequency, carrying out first pre-classification on the audio frequency, and determining the physiological phenomenon audio frequency and the common audio frequency;

frequency sweep signal appearance: the audio frequency is subjected to frequency detection, and the sound is subjected to second pre-classification by comparing with the frequency of the physiological phenomenon sample audio frequency to determine the physiological phenomenon audio frequency and the common audio frequency;

a signal processor: and the device is used for converting the physiological phenomenon audio and the common audio determined by the first pre-classification and the second pre-classification into physiological phenomenon electric signals and transmitting the physiological phenomenon electric signals to an audio processing device.

The working principle of the technical scheme is as follows:

the amplitude tester utilizes a linear vibration system to enable vibration signals to be overlapped with a plurality of harmonic vibrations through a spectrum analysis technology, the amplitude of the amplitude is measured, then, sound is pre-classified according to the incessant of the amplitude, the sound is divided into physiological phenomenon audio and common audio according to the amplitude, the number of pulses of the sound signals in each second is calculated through a sweep frequency signal instrument, and at the moment, the gate time is called as 1 second. The gate time may also be greater or less than one second. The longer the gating time, the more accurate the frequency value obtained, but the longer the gating time, the longer the interval during which no frequency is measured. The signal processor places a coil connected to the diaphragm in the magnetic field gap, and when a person speaks into the diaphragm, the coil vibrates in the magnetic field and generates an audio current by cutting the magnetic lines of force.

The beneficial effects of the above technical scheme are: the invention carries out sound amplitude detection and sound frequency detection on sound through the sweep frequency signal instrument of the vibration tester, further divides the sound into physiological phenomenon sound and common sound through the amplitude and the frequency, strips the physiological phenomenon sound from a large amount of sound through pre-classification, and carries out electric signal conversion on the physiological phenomenon sound and the common sound through the signal processor.

Example 4:

in one embodiment, the sound processing apparatus includes:

a noise remover: the physiological phenomenon electric signal is used for purifying the physiological phenomenon electric signal through a self-adaptive filter to obtain a pure physiological phenomenon electric signal;

an end point tester: the physiological phenomenon electric signal testing device is used for carrying out signal end point testing on the physiological phenomenon electric signal and determining the initial position of the physiological phenomenon electric signal;

a frame separator: and the device is used for framing the electric signal from the initial position of the physiological phenomenon electric signal, averagely dividing the electric signal into short-time stationary signals of small sections, and performing subsection analysis on the short-time stationary signals to obtain characteristic parameters.

The working principle of the technical scheme is as follows:

the denoising device tracks a time-varying input signal in an unknown environment to enable the input signal to be optimal, so that the denoising device is used for constructing a self-adaptive noise eliminator, carries out noise estimation on a signal with noise and subtracts a noise estimation value from an original signal to enhance voice; the endpoint tester determines the short-term energy and the average zero-crossing rate threshold value according to the observation, statistics and analysis of the physiological phenomenon sound template, and adopts a rear-end self-adaptive threshold value after detecting the physiological phenomenon sound endpoint by determining the condition of the initial point in the detection process and discharging a blank voice section according to the spectral entropy mean value, adjusts the threshold value to a proper value, determines the short-term energy and the average zero-crossing rate threshold value of each frame according to the characteristics of the physiological phenomenon sound, and determines the physiological phenomenon sound endpoint; calculating the number of the zero-crossing rate of the first 20 frames which is lower than the threshold value of the zero-crossing rate, calculating the average spectral entropy of the first 20 frames, judging whether the number of the zero-crossing rate of the first 20 frames and the average spectral entropy reach the standard or not, if so, ending the end point detection, otherwise, continuing the next end point detection; the framing device divides the physiological phenomenon electric signal into equal small segments, the framing is divided into continuous frames, the signal overlapping technology is adopted to enable the frames to be in smooth transition, the sequence of the physiological phenomenon electric signal is framed, a section of sampling value is multiplied by the length of the 1/2 frames, the longer the frame is, the smoother the signal is, the smaller the frame is, the signal has almost no smoothing effect, and therefore the length of the 1/2 frame is taken.

The beneficial effects of the above technical scheme are: the noise eliminator removes noise interference on the physiological phenomenon electric signal, and the noise interference has a negative effect on the physiological phenomenon voice recognition, so that pure physiological phenomenon voice is extracted from the noisy signal Zhang hong, the voice quality is improved, and the noise eliminator is an important link for recognizing the physiological phenomenon voice; the endpoint tester performs endpoint test on the physiological phenomenon sound, accurately finds the real position of the physiological phenomenon sound, eliminates the interference information such as silence or voice in continuous voice and the like, and improves the recognition rate in the subsequent process; the frame separator averagely divides the physiological phenomenon electric signal into short-time stable signals of all small sections, and analyzes the physiological phenomenon electric signal by adopting a short-time analysis technology, and the frame separation divides the electric signal into continuous frames so that the frames can be smoothly transited.

Example 5:

in one embodiment, the sound processing apparatus further comprises:

characteristic parameter extraction instrument: the method comprises the steps of extracting key characteristic parameters of short-time stationary signals of physiological phenomena through perceptual linear prediction;

physiological phenomenon audio memory: the physiological phenomenon electric signal sampling device is used for storing a physiological phenomenon electric signal sample acquired in reality and key characteristic parameters of the sample, and storing a threshold value set by the key characteristic parameters;

physiological sound signal classification device: the short-time stationary signal classification method is used for sampling key characteristic parameters of the short-time stationary signal and classifying the short-time stationary signal according to the comparison between the sampling and the threshold value.

The working principle of the technical scheme is as follows:

the linear prediction is used for sampling key characteristic parameters of the physiological phenomenon to form a linear prediction sampling combination, carrying out least square error approximation between the actual physiological phenomenon voice signal and the linear prediction sampling, and classifying the physiological phenomenon voice signal when the least square error reaches one threshold;

the beneficial effects of the above technical scheme are: the characteristic parameter extractor selects parameters which can represent the sound characteristics of the physiological phenomenon, the parameters can effectively represent the sound characteristics of the physiological phenomenon, the characteristic parameter extractor has good distinguishability, does not change along with the change of time and space, and is easy to extract from a plurality of sounds; the physiological phenomenon audio memory stores a physiological phenomenon sound template of the mobile phone, so that a threshold value is conveniently called; comparing the physiological sound signal classification equipment with the sampling of the short-time steady signal, and rapidly classifying the audio;

example 6:

in one embodiment, the characteristic parameter analysis device includes:

characteristic parameter analysis equipment: classifying the short-time stationary signals into cough short-time stationary signals, sigh short-time stationary signals and unvoiced sound short-time stationary signals according to the comparison result, and matching different processing modes according to the classification;

matching equipment: and the signal processing mode is used for receiving and matching the classified signals.

The working principle of the technical scheme is as follows:

the characteristic parameter analysis equipment analyzes the electric signal by a fixed sliding window, the time domain sliding window processing filters the signal in frequency division, filters the signal which does not meet the characteristic parameter of the physiological phenomenon sound signal, classifies the signal in detail according to the characteristics of the physiological phenomenon sound signal, and the matching equipment sets initial processing operation corresponding to each classification and can also set different operation commands and algorithms according to different connecting equipment.

The beneficial effects of the above technical scheme are: the characteristic parameter analysis equipment of the invention classifies the short-time stationary signals more finely according to the comparison result of the sampling and the threshold value, and matches the classified physiological phenomenon voice with a corresponding signal processing mode, and the processing mode can be changed according to the requirements of different equipment.

Example 7:

in one embodiment, the matching device comprises:

cough electrical signal processor: the device is used for sending out a delay operation initial command to the detected cough electric signal, and different operation commands can be set according to different devices;

sigh electrical signal processor: the system is used for sending a slowing operation initial command to the detected sigh electric signal, and different operation commands can be set according to different equipment;

the throat-clearing sound electric signal processor: the voice detector is used for sending a pause operation initial command to the detected unvoiced sound electric signal, and different operation commands can be set according to different devices.

The working principle of the technical scheme is as follows:

the coughing electric signal processor sends out a delayed operation initial command when receiving the coughing electric signal, and different operation commands can be set according to different equipment; the unvoiced sound electric signal processor is used for sending out a pause operation initial command to the detected unvoiced sound electric signal, and different operation commands can be set according to different equipment.

The beneficial effects of the above technical scheme are: the matching device comprises three main processors, wherein the three main processors are all provided with initial processing operation commands, and different operation commands are set according to different algorithms of the processors and different connected devices.

Example 8:

in one embodiment, as shown in FIG. 3, the end point tester comprises the steps of:

s1: determining the condition of a starting point in the detection process, and discharging a blank voice section according to the mean value of the spectral entropy;

s2: after a physiological phenomenon sound endpoint is detected, a back-end self-adaptive threshold is adopted, and a threshold value is adjusted to a proper value;

s3: determining the short-time energy and average zero-crossing rate threshold of each frame according to the characteristics of the physiological phenomenon sound, and determining a physiological phenomenon sound endpoint;

s4, calculating the number of the zero crossing rate of the first 20 frames lower than the threshold value of the zero crossing rate, and calculating the average spectral entropy of the first 20 frames;

s5: and (4) judging whether the zero-crossing rate number and the average spectral entropy of the first 20 frames reach the standard, if so, finishing the end point detection, otherwise, continuing the next end point detection, and turning to the step S1.

The working principle of the technical scheme is as follows:

determining the condition of the starting point in the detection process, discharging blank speech segments according to the mean value of the spectral entropy, detecting the starting point of the physiological phenomenon sound, setting an initial value LIY, starting from the 1 st frame, successively comparing the average amplitude of each frame, wherein M1 is the frame number of the first frame of the average amplitude, if the subsequent average amplitude exceeds the previous amplitude, then the original M1 is not taken as the initial starting point, the next average amplitude exceeding the previous one is taken as M1, and the value of MI is greater than the initial value, and so on, stopping comparison when finding the frame with the first maximum average amplitude, detecting a physiological phenomenon sound end point M2, searching backwards frame by frame from an initial point M1, if the average amplitude of 20 continuous frames is lower than the initial value LIY and the zero crossing rate of more than 5 frames is lower than the average value NHY, taking the first frame as a physiological phenomenon sound end point M2, and finally discharging blank voice sections according to the spectrum entropy mean value;

after the physiological phenomenon voice end point is detected, a back end self-adaptive threshold value is adopted, the threshold value is adjusted to a proper value, and the initial threshold value is RFRV-MIN [ IJN, p ]

After the end point is detected, the threshold value is updated by using the value of the last 5 frames of the end point M2, and the threshold value is updated according to the following formula:

LIY＝M×NHY+(2-M)×NHY

NHY＝2.5M

IEG＝M×IEG·1+(2-M)×IEG·2

wherein, M is weight value, the assignment value is 0.9, LIY is initial value, NHY is amplitude average value, IEG is current calculated threshold value, IEG 1 and IEG 2 are previous used threshold value; the generation of physiological phenomenon voice is uncontrollable, an initial threshold value is taken as RFRV to detect the first cough as soon as possible, and then a self-adaptive threshold value is adopted to gradually adjust the threshold value to a proper value;

the beneficial effects of the above technical scheme are: the invention eliminates the blank voice section in the first step of the end point tester, sets the threshold value for the left audio, and carries out end point detection through the complete steps, thereby preventing the occurrence of the missing audio and the blank audio.

Example 9:

in one embodiment, the sound processing apparatus further comprises:

the non-voice sound signal detector comprises: the method is used for analyzing the sound signals emitted by the organs or joints of the human body, determining the distribution of the physiological sound signals in the frequency domain, and performing frequency spectrum analysis on the organs or joints according to the frequency domain information to determine the illness state of the patient.

The working principle of the technical scheme is as follows:

the method comprises the steps of carrying out signal detection on a physiological signal, judging the physiological condition of a patient according to a spectrogram of an analysis physiological signal, diagnosing arthritis according to collected joint sounds, analyzing a sound signal emitted by a human organ or joint to determine the distribution of the physiological signal in a frequency domain, carrying out spectrum analysis on the organ or joint according to frequency domain information, and determining the state of an illness of the patient.

The beneficial effects of the above technical scheme are: in the past, doctors intelligently rely on stethoscopes to listen to the sounds and judge according to experience, so that the judgment is very inaccurate, but physiological signals in a frequency domain can judge the physiological condition of the human body according to spectral analysis, and therefore patients can be treated more accurately.

Example 10:

in one embodiment, the sound processing apparatus further comprises:

a signal doubler: after the noise eliminator, the high-frequency part of the pure electric signal is pre-emphasized through A/D conversion, and the dynamic range of the physiological phenomenon sound signal is compressed to obtain a high signal-to-noise ratio which is used for enhancing the physiological phenomenon sound signal.

The working principle of the technical scheme is as follows:

like speech signal, the high frequency part of physiology phenomenon sound can receive the influence of door excitation and oronasal radiation and weaken, through AD transform, can not only cross the pre-emphasis like this, can also compress the dynamic range of signal to improve the SNR, strengthen the signal of physiology phenomenon sound.

The beneficial effects of the above technical scheme are: the electric signal is affected by door excitation and oral-nasal radiation as a voice signal, and the high-frequency part is attenuated, so that the high-frequency part of the pure electric signal needs to be pre-emphasized through A/D conversion, and the electric signal can be restored to the original characteristic in the analysis of the signal.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.